© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7705
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and syntax often used in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteBehavior
    -0.78
    IsContent
    -0.70
    تقاوى
    -0.64
    XMLSchema
    -0.57
    CodedInputStream
    -0.57
    AntiForgeryToken
    -0.56
    aronder
    -0.55
    xaml
    -0.55
    ModelSerializer
    -0.55
    +#+#
    -0.54
    POSITIVE LOGITS
     initWith
    0.99
    initWith
    0.86
     numberWith
    0.73
    initWithFrame
    0.64
    zugehen
    0.61
     actionMode
    0.60
    edipus
    0.59
    Mozilla
    0.58
    iseries
    0.56
    vás
    0.55
    Activations Density 0.100%

    No Known Activations